{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/speech-recognition/papers/54","list_of":"/task/speech-recognition","task":"Speech Recognition","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":54,"pages_in_order":65,"rows_per_page":100,"rows":[5301,5400],"of":6433,"counts":{"archive_papers_tagged":6433,"with_a_code_link":1373,"where_syntology_ran_a_sample":196,"not_listed_spam_title":0,"listed":6433,"listed_where_code_ran":196,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":162,"every_run_a_failure_of_syntologys_instrument":34,"listed_with_a_run_with_no_instrument_failure":162,"listed_every_run_a_failure_of_syntologys_instrument":34,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/speech-recognition","prev":"/task/speech-recognition/papers/53","next":"/task/speech-recognition/papers/55","papers":[{"url":null,"slug":"deep-feed-forward-sequential-memory-networks","title":"Deep Feed-forward Sequential Memory Networks for Speech Synthesis","date":"2018-02-26","arxiv_id":"1802.09194","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-speech-recognition-and-topic","title":"Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages","date":"2018-02-23","arxiv_id":"1802.08731","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-order-recurrent-neural-networks-for","title":"High Order Recurrent Neural Networks for Acoustic Modelling","date":"2018-02-22","arxiv_id":"1802.08314","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-predictive-coding-using-convolutional","title":"Neural Predictive Coding using Convolutional Neural Networks towards Unsupervised Learning of Speaker Characteristics","date":"2018-02-22","arxiv_id":"1802.07860","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequence-based-multi-lingual-low-resource","title":"Sequence-based Multi-lingual Low Resource Speech Recognition","date":"2018-02-21","arxiv_id":"1802.07420","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-knowledge-using-parallel-data-for","title":"Distilling Knowledge Using Parallel Data for Far-field Speech Recognition","date":"2018-02-20","arxiv_id":"1802.06941","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-tdnns-using-deep-kernels-and","title":"Improved TDNNs using Deep Kernels and Frequency Dependent Grid-RNNs","date":"2018-02-18","arxiv_id":"1802.06412","repositories_listed":0,"syntology":null},{"url":"/paper/visual-only-recognition-of-normal-whispered","slug":"visual-only-recognition-of-normal-whispered","title":"Visual-Only Recognition of Normal, Whispered and Silent Speech","date":"2018-02-18","arxiv_id":"1802.06399","repositories_listed":0,"syntology":null},{"url":null,"slug":"articulatory-information-and-multiview","title":"Articulatory information and Multiview Features for Large Vocabulary Continuous Speech Recognition","date":"2018-02-16","arxiv_id":"1802.05853","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpreting-dnn-output-layer-activations-a","title":"Interpreting DNN output layer activations: A strategy to cope with unseen data in speech recognition","date":"2018-02-16","arxiv_id":"1802.06861","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-lip-reading-using-audio","title":"Deep Learning for Lip Reading using Audio-Visual Information for Urdu Language","date":"2018-02-15","arxiv_id":"1802.05521","repositories_listed":0,"syntology":null},{"url":null,"slug":"deceiving-end-to-end-deep-learning-malware","title":"Deceiving End-to-End Deep Learning Malware Detectors using Adversarial Examples","date":"2018-02-13","arxiv_id":"1802.04528","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-based-curriculum-learning-for-end","title":"Structured-based Curriculum Learning for End-to-end English-Japanese Speech Translation","date":"2018-02-13","arxiv_id":"1802.06003","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-modeling-of-accents-and-acoustics-for","title":"Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition","date":"2018-02-07","arxiv_id":"1802.02656","repositories_listed":0,"syntology":null},{"url":"/paper/multi-temporal-land-cover-classification-with","slug":"multi-temporal-land-cover-classification-with","title":"Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders","date":"2018-02-06","arxiv_id":"1802.02080","repositories_listed":0,"syntology":null},{"url":null,"slug":"phonetic-and-graphemic-systems-for-multi","title":"Phonetic and Graphemic Systems for Multi-Genre Broadcast Transcription","date":"2018-02-01","arxiv_id":"1802.00254","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-works-in-practice-but-does-it","title":"Deep Learning Works in Practice. But Does it Work in Theory?","date":"2018-01-31","arxiv_id":"1801.10437","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-recurrent-neural-network-1","title":"Accelerating recurrent neural network language model based online speech recognition system","date":"2018-01-30","arxiv_id":"1801.09866","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-corpus-for-modeling-word-importance-in","title":"A Corpus for Modeling Word Importance in Spoken Dialogue Transcripts","date":"2018-01-29","arxiv_id":"1801.09746","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-biometrics-for-twins-identification","title":"A Multi-Biometrics for Twins Identification Based Speech and Ear","date":"2018-01-27","arxiv_id":"1801.09056","repositories_listed":0,"syntology":null},{"url":null,"slug":"commandersong-a-systematic-approach-for","title":"CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition","date":"2018-01-24","arxiv_id":"1801.08535","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-training-and-cross-lingual","title":"Multilingual Training and Cross-lingual Adaptation on CTC-based Acoustic Model","date":"2018-01-23","arxiv_id":"1711.10025","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hardware-friendly-algorithm-for-scalable","title":"A Hardware-Friendly Algorithm for Scalable Training and Deployment of Dimensionality Reduction Models on FPGA","date":"2018-01-11","arxiv_id":"1801.04014","repositories_listed":0,"syntology":null},{"url":null,"slug":"conversational-ai-the-science-behind-the","title":"Conversational AI: The Science Behind the Alexa Prize","date":"2018-01-11","arxiv_id":"1801.03604","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-forecasting-stock-returns","title":"Deep Learning for Forecasting Stock Returns in the Cross-Section","date":"2018-01-03","arxiv_id":"1801.01777","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-architectures-data-and-units-for","title":"Exploring Architectures, Data and Units For Streaming End-to-End Speech Recognition with RNN-Transducer","date":"2018-01-02","arxiv_id":"1801.00841","repositories_listed":0,"syntology":null},{"url":null,"slug":"clipping-free-attacks-against-neural-networks","title":"Clipping Free Attacks Against Neural Networks","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-institutional-dialog-acts-in-police","title":"Detecting Institutional Dialog Acts in Police Traffic Stops","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-node-embeddings-learning-ego-centric","title":"Fast Node Embeddings: Learning Ego-Centric Representations","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gated-convnets-for-letter-based-asr","title":"Gated ConvNets for Letter-Based ASR","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-deep-compression-compressing-deep","title":"Iterative Deep Compression : Compressing Deep Networks for Classification and Semantic Segmentation","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-modeling-for-morphologically-rich","title":"Language Modeling for Morphologically Rich Languages: Character-Aware Modeling for Word-Level Prediction","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-multi-domain-multi-task-learning","title":"Large Scale Multi-Domain Multi-Task Learning with MultiModel","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"link-weight-prediction-with-node-embeddings","title":"Link Weight Prediction with Node Embeddings","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"new-baseline-in-automatic-speech-recognition","title":"New Baseline in Automatic Speech Recognition for Northern S\\'ami","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"phonologically-informed-edit-distance","title":"Phonologically Informed Edit Distance Algorithms for Word Alignment with Low-Resource Languages","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pronouncur-an-urdu-pronunciation-lexicon","title":"PronouncUR: An Urdu Pronunciation Lexicon Generator","date":"2018-01-01","arxiv_id":"1801.00409","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-capio-2017-conversational-speech","title":"The CAPIO 2017 Conversational Speech Recognition System","date":"2017-12-29","arxiv_id":"1801.00059","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-do-we-need-to-build-explainable-ai","title":"What do we need to build explainable AI systems for the medical domain?","date":"2017-12-28","arxiv_id":"1712.09923","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-native-language-speech-for-accent","title":"Leveraging Native Language Speech for Accent Identification using Deep Siamese Networks","date":"2017-12-25","arxiv_id":"1712.08992","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-using-backpropagation-for-speech-texture","title":"On Using Backpropagation for Speech Texture Generation and Voice Conversion","date":"2017-12-22","arxiv_id":"1712.08363","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-regularization-techniques-for-end-to","title":"Improved Regularization Techniques for End-to-End Speech Recognition","date":"2017-12-19","arxiv_id":"1712.07108","repositories_listed":0,"syntology":null},{"url":"/paper/improving-end-to-end-speech-recognition-with-1","slug":"improving-end-to-end-speech-recognition-with-1","title":"Improving End-to-End Speech Recognition with Policy Learning","date":"2017-12-19","arxiv_id":"1712.07101","repositories_listed":0,"syntology":null},{"url":null,"slug":"subword-and-crossword-units-for-ctc-acoustic","title":"Subword and Crossword Units for CTC Acoustic Models","date":"2017-12-19","arxiv_id":"1712.06855","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-distant-speech-recognition","title":"Deep Learning for Distant Speech Recognition","date":"2017-12-17","arxiv_id":"1712.06086","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-berkeley-view-of-systems-challenges-for-ai","title":"A Berkeley View of Systems Challenges for AI","date":"2017-12-15","arxiv_id":"1712.05855","repositories_listed":0,"syntology":null},{"url":null,"slug":"fft-based-deep-learning-deployment-in","title":"FFT-Based Deep Learning Deployment in Embedded Systems","date":"2017-12-13","arxiv_id":"1712.04910","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-robust-dialog-policies-in-noisy","title":"Learning Robust Dialog Policies in Noisy Environments","date":"2017-12-11","arxiv_id":"1712.04034","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-competitive-direct-acoustics-to-word","title":"Building competitive direct acoustics-to-word models for English conversational speech recognition","date":"2017-12-08","arxiv_id":"1712.03133","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-analysis-of-incorporating-an-external","title":"An analysis of incorporating an external language model into a sequence-to-sequence model","date":"2017-12-06","arxiv_id":"1712.01996","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-dialect-speech-recognition-with-a","title":"Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Model","date":"2017-12-05","arxiv_id":"1712.01541","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuraghe-exploiting-cpu-fpga-synergies-for","title":"NEURAghe: Exploiting CPU-FPGA Synergies for Efficient and Flexible CNN Inference Acceleration on Zynq SoCs","date":"2017-12-04","arxiv_id":"1712.00994","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-scaling-is-predictable","title":"Deep Learning Scaling is Predictable, Empirically","date":"2017-12-01","arxiv_id":"1712.00409","repositories_listed":0,"syntology":null},{"url":null,"slug":"houdini-fooling-deep-structured-visual-and","title":"Houdini: Fooling Deep Structured Visual and Speech Recognition Models with Adversarial Examples","date":"2017-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-end-to-end-memory-networks-with","title":"Improving End-to-End Memory Networks with Unified Weight Tying","date":"2017-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-features-for-context-aware-speech","title":"Visual Features for Context-Aware Speech Recognition","date":"2017-12-01","arxiv_id":"1712.00489","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-nontrivial-connectivity-for","title":"Exploiting Nontrivial Connectivity for Automatic Speech Recognition","date":"2017-11-28","arxiv_id":"1711.10271","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-long-short-term-memory-adaptive","title":"Deep Long Short-Term Memory Adaptive Beamforming Networks For Multichannel Robust Speech Recognition","date":"2017-11-21","arxiv_id":"1711.08016","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-adaptation-with-domain","title":"Unsupervised Adaptation with Domain Separation Networks for Robust Speech Recognition","date":"2017-11-21","arxiv_id":"1711.08010","repositories_listed":0,"syntology":null},{"url":null,"slug":"e-pur-an-energy-efficient-processing-unit-for","title":"E-PUR: An Energy-Efficient Processing Unit for Recurrent Neural Networks","date":"2017-11-20","arxiv_id":"1711.07480","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-recognition-for-medical-conversations","title":"Speech recognition for medical conversations","date":"2017-11-20","arxiv_id":"1711.07274","repositories_listed":0,"syntology":null},{"url":null,"slug":"chipmunk-a-systolically-scalable-09-mm2-308","title":"Chipmunk: A Systolically Scalable 0.9 mm${}^2$, 3.08 Gop/s/mW @ 1.2 mW Accelerator for Near-Sensor Recurrent Neural Network Inference","date":"2017-11-15","arxiv_id":"1711.05734","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-speech-enhancement-with-generative","title":"Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition","date":"2017-11-15","arxiv_id":"1711.05747","repositories_listed":0,"syntology":null},{"url":null,"slug":"lattice-rescoring-strategies-for-long-short","title":"Lattice Rescoring Strategies for Long Short Term Memory Language Models in Speech Recognition","date":"2017-11-15","arxiv_id":"1711.05448","repositories_listed":0,"syntology":null},{"url":null,"slug":"supervised-and-unsupervised-transfer-learning","title":"Supervised and Unsupervised Transfer Learning for Question Answering","date":"2017-11-14","arxiv_id":"1711.05345","repositories_listed":0,"syntology":null},{"url":null,"slug":"phonemic-and-graphemic-multilingual-ctc-based","title":"Phonemic and Graphemic Multilingual CTC Based Speech Recognition","date":"2017-11-13","arxiv_id":"1711.04564","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-of-speech-recognition","title":"Reinforcement Learning of Speech Recognition System Based on Policy Gradient and Hypothesis Selection","date":"2017-11-10","arxiv_id":"1711.03689","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-dropout-in-online-learning","title":"Analysis of Dropout in Online Learning","date":"2017-11-09","arxiv_id":"1711.03343","repositories_listed":0,"syntology":null},{"url":null,"slug":"feed-forward-and-backward-run-in-deep","title":"Feed Forward and Backward Run in Deep Convolution Neural Network","date":"2017-11-09","arxiv_id":"1711.03278","repositories_listed":0,"syntology":null},{"url":null,"slug":"block-sparse-recurrent-neural-networks","title":"Block-Sparse Recurrent Neural Networks","date":"2017-11-08","arxiv_id":"1711.02782","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-speech-recognition-with-a-single","title":"Multilingual Speech Recognition With A Single End-To-End Model","date":"2017-11-06","arxiv_id":"1711.01694","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-language-universal-end-to-end-speech","title":"Towards Language-Universal End-to-End Speech Recognition","date":"2017-11-06","arxiv_id":"1711.02207","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-speech-recognition-using-generative","title":"Robust Speech Recognition Using Generative Adversarial Networks","date":"2017-11-05","arxiv_id":"1711.01567","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-language-models-for-code-switched-speech","title":"Dual Language Models for Code Switched Speech Recognition","date":"2017-11-03","arxiv_id":"1711.01048","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-parallel-recurrent-neural-network-for","title":"A Parallel Recurrent Neural Network for Language Modeling with POS Tags","date":"2017-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"aoa-e-eea13c-14eae3e34-ee-eaa-aa-on-the-use","title":"序列標記與配對方法用於語音辨識錯誤偵測及修正 (On the Use of Sequence Labeling and Matching Methods for ASR Error Detection and Correction) [In Chinese]","date":"2017-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"attentive-language-models","title":"Attentive Language Models","date":"2017-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"can-discourse-relations-be-identified","title":"Can Discourse Relations be Identified Incrementally?","date":"2017-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-black-box-speech-recognition-using","title":"Improving Black-box Speech Recognition using Semantic Parsing","date":"2017-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-learning-of-dialog-act-segmentation-and","title":"Joint Learning of Dialog Act Segmentation and Recognition in Spoken Dialog Using Neural Networks","date":"2017-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-method-for-improving-arabic","title":"Unsupervised Method for Improving Arabic Speech Recognition Systems","date":"2017-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-teacher-student-model-for-emotional","title":"Using Teacher-Student Model For Emotional Speech Recognition[In Chinese]","date":"2017-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-supervised-stdp-based-training-algorithm","title":"A Supervised STDP-based Training Algorithm for Living Neural Networks","date":"2017-10-30","arxiv_id":"1710.10944","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-neural-trans-dimensional-random","title":"Learning neural trans-dimensional random field language models with noise-contrastive estimation","date":"2017-10-30","arxiv_id":"1710.10739","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequence-to-sequence-asr-optimization-via","title":"Sequence-to-Sequence ASR Optimization via Reinforcement Learning","date":"2017-10-30","arxiv_id":"1710.10774","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-all-convolutional-encoders-for","title":"A Study of All-Convolutional Encoders for Connectionist Temporal Classification","date":"2017-10-28","arxiv_id":"1710.10398","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridgenets-student-teacher-transfer-learning","title":"BridgeNets: Student-Teacher Transfer Learning Based on Recursive Neural Networks and its Application to Distant Speech Recognition","date":"2017-10-27","arxiv_id":"1710.10224","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-neural-networks","title":"Deep Neural Networks","date":"2017-10-25","arxiv_id":"1710.09302","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-multiple-views-for-visual-speech","title":"Combining Multiple Views for Visual Speech Recognition","date":"2017-10-19","arxiv_id":"1710.07168","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-speech-recognition-using-pca-networks","title":"Visual Speech Recognition Using PCA Networks and LSTMs in a Tandem GMM-HMM System","date":"2017-10-19","arxiv_id":"1710.07161","repositories_listed":0,"syntology":null},{"url":null,"slug":"embedding-based-speaker-adaptive-training-of","title":"Embedding-Based Speaker Adaptive Training of Deep Neural Networks","date":"2017-10-17","arxiv_id":"1710.06937","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-general-purpose-speech-recognition","title":"Adapting general-purpose speech recognition engine output for domain-specific natural language question answering","date":"2017-10-12","arxiv_id":"1710.06923","repositories_listed":0,"syntology":null},{"url":null,"slug":"convolutional-attention-based-seq2seq-neural","title":"Convolutional Attention-based Seq2Seq Neural Network for End-to-End ASR","date":"2017-10-12","arxiv_id":"1710.04515","repositories_listed":0,"syntology":null},{"url":null,"slug":"keynote-small-neural-nets-are-beautiful","title":"Keynote: Small Neural Nets Are Beautiful: Enabling Embedded Systems with Small Deep-Neural-Network Architectures","date":"2017-10-07","arxiv_id":"1710.02759","repositories_listed":0,"syntology":null},{"url":null,"slug":"syntactic-and-semantic-features-for-code","title":"Syntactic and Semantic Features For Code-Switching Factored Language Models","date":"2017-10-04","arxiv_id":"1710.01809","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoding-visemes-improving-machine-lipreading","title":"Decoding visemes: improving machine lipreading","date":"2017-10-03","arxiv_id":"1710.01288","repositories_listed":0,"syntology":null},{"url":null,"slug":"resolution-limits-on-visual-speech","title":"Resolution limits on visual speech recognition","date":"2017-10-03","arxiv_id":"1710.01073","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-speech-recognition-aligning","title":"Visual speech recognition: aligning terminologies for better understanding","date":"2017-10-03","arxiv_id":"1710.01292","repositories_listed":0,"syntology":null},{"url":null,"slug":"which-phoneme-to-viseme-maps-best-improve","title":"Which phoneme-to-viseme maps best improve visual-only computer lip-reading?","date":"2017-10-03","arxiv_id":"1710.01093","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepsafe-a-data-driven-approach-for-checking","title":"DeepSafe: A Data-driven Approach for Checking Adversarial Robustness in Neural Networks","date":"2017-10-02","arxiv_id":"1710.00486","repositories_listed":0,"syntology":null}],"record_sha256":"19a888be457fbd6cfc140d8e9c2726fd0fe8cc143bb3a8badfbf2a6a51246874","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}